题 目：Social Analysis by Using Large-Scale Broadcast Video Archive
讲 者：Prof. Shin'ichi Satoh
时 间：2018年11月 20日15:15-15:50
地 点： 国家多媒体软件工程技术中心6楼南613会议室
We can obtain a large amount of useful information aspects simply by watching television, e.g., details about events in Japan and in the world, current trends, economic activities, and so on. In a few experimental studies, we have explored how this data can be used for automated social analysis through fast commercial film mining, visual semantic classification, and visual object retrieval tools. In my lab, we developed and deployed key technologies for analyzing the NII TV-RECS video archive containing 400,000 hours of broadcast videos to achieve this goal. In this talk, I will present a selection of our work that describes methods to automatically extract and analyze such information.
Prof. Shin'ichi Satoh received his BE, ME and Ph.D. degrees at the University of Tokyo. He is a full professor at National Institute of Informatics (NII), Tokyo, since 2004. He is also a professor at the University of Tokyo, and the director of Research Center for Medical Big Data, NII. He was a visiting scientist at the Robotics Institute, Carnegie Mellon University, from 1995 to 1997. Prof. Satoh is a follow of IEICE and ITE Japan. He has served as Editorial Board/Associate Editor for lots of top Journals, such as IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology, and International Journal of Computer Vision. He served as General Co-chair of ACM International Conference on Multimedia Retrieval 2018. His papers won the Best Paper Award of ICMR 2017, Honorable Mention Poster of IEEE PacificVis 2017, and Best Honorable Mention Paper Award of ISM 2016. His team won the first place at TRECVID Instance Search in 2011, 2013, 2014.